Training Complete.

config.json

@@ -0,0 +1,64 @@
+{
+  "_name_or_path": "Helsinki-NLP/opus-mt-en-zh",
+  "activation_dropout": 0.0,
+  "activation_function": "swish",
+  "add_bias_logits": false,
+  "add_final_layer_norm": false,
+  "architectures": [
+    "MarianMTModel"
+  ],
+  "attention_dropout": 0.0,
+  "bad_words_ids": [
+    [
+      65000
+    ]
+  ],
+  "bos_token_id": 0,
+  "classif_dropout": 0.0,
+  "classifier_dropout": 0.0,
+  "d_model": 512,
+  "decoder_attention_heads": 8,
+  "decoder_ffn_dim": 2048,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 65000,
+  "decoder_vocab_size": 65001,
+  "do_blenderbot_90_layernorm": false,
+  "dropout": 0.1,
+  "encoder_attention_heads": 8,
+  "encoder_ffn_dim": 2048,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_token_id": 0,
+  "extra_pos_embeddings": 0,
+  "force_bos_token_to_be_generated": false,
+  "forced_eos_token_id": 0,
+  "gradient_checkpointing": false,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "max_length": 512,
+  "max_position_embeddings": 512,
+  "model_type": "marian",
+  "normalize_before": false,
+  "normalize_embedding": false,
+  "num_beams": 4,
+  "num_hidden_layers": 6,
+  "pad_token_id": 65000,
+  "scale_embedding": true,
+  "share_encoder_decoder_embeddings": true,
+  "static_position_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.24.0",
+  "use_cache": true,
+  "vocab_size": 65001
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3342868302ff33fc6fb3b44eee342f55ff5fe9fc9fb1aa368ff1821928418114
+size 619500986

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:baadbc2307097d48582555d179d9ad0e07e7116c580e3f3b4b8a1d790ac688e7
+size 310022978

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81e3bed1284e9e0f46581fe18cc7d8d206f28cb1d88d71c56fed7e0d7b815e34
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47ba861fa57ead88162a370836024df8c5acb4616e84d2ab687ab69abd4c484f
+size 1064

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "eos_token": "</s>",
+  "model_max_length": 512,
+  "name_or_path": "Helsinki-NLP/opus-mt-en-zh",
+  "pad_token": "<pad>",
+  "return_tensor": "pt",
+  "separate_vocabs": false,
+  "source_lang": "eng",
+  "sp_model_kwargs": {},
+  "special_tokens_map_file": null,
+  "target_lang": "zho",
+  "tokenizer_class": "MarianTokenizer",
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,154 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 11787,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9151607703402055e-05,
+      "loss": 1.5519,
+      "step": 500
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.8303215406804106e-05,
+      "loss": 1.35,
+      "step": 1000
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.745482311020616e-05,
+      "loss": 1.2666,
+      "step": 1500
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.6606430813608214e-05,
+      "loss": 1.2182,
+      "step": 2000
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1.5758038517010267e-05,
+      "loss": 1.1894,
+      "step": 2500
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 1.490964622041232e-05,
+      "loss": 1.2037,
+      "step": 3000
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.4061253923814373e-05,
+      "loss": 1.1514,
+      "step": 3500
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 1.3212861627216427e-05,
+      "loss": 1.113,
+      "step": 4000
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 1.2364469330618477e-05,
+      "loss": 1.018,
+      "step": 4500
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 1.1516077034020531e-05,
+      "loss": 1.0139,
+      "step": 5000
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 1.0667684737422585e-05,
+      "loss": 1.0093,
+      "step": 5500
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 9.819292440824639e-06,
+      "loss": 1.0084,
+      "step": 6000
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 8.970900144226691e-06,
+      "loss": 1.0089,
+      "step": 6500
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 8.122507847628745e-06,
+      "loss": 0.9934,
+      "step": 7000
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 7.274115551030797e-06,
+      "loss": 0.9786,
+      "step": 7500
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 6.425723254432851e-06,
+      "loss": 0.9493,
+      "step": 8000
+    },
+    {
+      "epoch": 2.16,
+      "learning_rate": 5.577330957834903e-06,
+      "loss": 0.9069,
+      "step": 8500
+    },
+    {
+      "epoch": 2.29,
+      "learning_rate": 4.728938661236957e-06,
+      "loss": 0.9056,
+      "step": 9000
+    },
+    {
+      "epoch": 2.42,
+      "learning_rate": 3.88054636463901e-06,
+      "loss": 0.9129,
+      "step": 9500
+    },
+    {
+      "epoch": 2.55,
+      "learning_rate": 3.0321540680410622e-06,
+      "loss": 0.929,
+      "step": 10000
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 2.1837617714431156e-06,
+      "loss": 0.9058,
+      "step": 10500
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 1.3353694748451684e-06,
+      "loss": 0.9086,
+      "step": 11000
+    },
+    {
+      "epoch": 2.93,
+      "learning_rate": 4.869771782472216e-07,
+      "loss": 0.9055,
+      "step": 11500
+    }
+  ],
+  "max_steps": 11787,
+  "num_train_epochs": 3,
+  "total_flos": 4684090101792768.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9caf7bd8a753cafd017354b9cede467e6233e2cd52eb195969931b536145eecd
+size 4024